Quantization Backdoors to Deep Learning Commercial Frameworks. (arXiv:2108.09187v3 [cs.CR] UPDATED)

Currently, there is a burgeoning demand for deploying deep learning (DL)
models on ubiquitous edge Internet of Things (IoT) devices attributed to their
low latency and high privacy preservation. However, DL models are often large
in size and require large-scale computation, which prevents them from being
placed directly onto IoT devices, where resources are constrained and 32-bit
floating-point (float-32) operations are unavailable. Commercial framework
(i.e., a set of toolkits) empowered model quantization is a pragmatic solution
that enables DL deployment …

backdoors commercial computation deep learning demand deployment devices edge embedded embedded systems empowered framework frameworks high internet internet of things iot iot devices large latency low mobile mobile devices operations point preservation privacy resources scale size solution systems things